[ARM] Cortex-A57 scheduling model for ARM backend (AArch32)

This patch implements the Cortex-A57 scheduling model. The main code is in ARMScheduleA57.td, ARMScheduleA57WriteRes.td. Small changes in cpp,.h files to support required scheduling predicates. Scheduling model implemented according to: http://infocenter.arm.com/help/topic/com.arm.doc.uan0015b/Cortex_A57_Software_Optimization_Guide_external.pdf. Patch by : Andrew Zhogin (submitted on his behalf, as requested). Rewiewed by: Renato Golin, Diana Picus, Javed Absar, Kristof Beyls. Differential Revision: https://reviews.llvm.org/D28152 llvm-svn: 304530
llvm · Jun 2, 2017 · 4ae7e81 · 4ae7e81
1 parent fee75f4
commit 4ae7e81
Showing 19 changed files with 2,404 additions and 11 deletions.
diff --git a/llvm/include/llvm/CodeGen/TargetSchedule.h b/llvm/include/llvm/CodeGen/TargetSchedule.h
@@ -55,6 +55,9 @@ class TargetSchedModel {
   /// Return the MCSchedClassDesc for this instruction.
   const MCSchedClassDesc *resolveSchedClass(const MachineInstr *MI) const;
 
+  /// \brief TargetSubtargetInfo getter.
+  const TargetSubtargetInfo *getSubtargetInfo() const { return STI; }
+
   /// \brief TargetInstrInfo getter.
   const TargetInstrInfo *getInstrInfo() const { return TII; }
 

diff --git a/llvm/lib/Target/ARM/ARM.td b/llvm/lib/Target/ARM/ARM.td
@@ -205,6 +205,13 @@ def FeatureAvoidPartialCPSR : SubtargetFeature<"avoid-partial-cpsr",
                                                "AvoidCPSRPartialUpdate", "true",
                                  "Avoid CPSR partial update for OOO execution">;
 
+/// Disable +1 predication cost for instructions updating CPSR.
+/// Enabled for Cortex-A57.
+def FeatureCheapPredicableCPSR : SubtargetFeature<"cheap-predicable-cpsr",
+                                                  "CheapPredicableCPSRDef",
+                                                  "true",
+                  "Disable +1 predication cost for instructions updating CPSR">;
+
 def FeatureAvoidMOVsShOp : SubtargetFeature<"avoid-movs-shop",
                                             "AvoidMOVsShifterOperand", "true",
                                 "Avoid movs instructions with shifter operand">;
@@ -788,12 +795,14 @@ def : ProcNoItin<"cortex-a53",                          [ARMv8a, ProcA53,
                                                          FeatureCRC,
                                                          FeatureFPAO]>;
 
-def : ProcNoItin<"cortex-a57",                          [ARMv8a, ProcA57,
-                                                         FeatureHWDivThumb,
-                                                         FeatureHWDivARM,
-                                                         FeatureCrypto,
-                                                         FeatureCRC,
-                                                         FeatureFPAO]>;
+def : ProcessorModel<"cortex-a57",  CortexA57Model, [ARMv8a, ProcA57,
+                                                     FeatureHWDivThumb,
+                                                     FeatureHWDivARM,
+                                                     FeatureCrypto,
+                                                     FeatureCRC,
+                                                     FeatureFPAO,
+                                                     FeatureAvoidPartialCPSR,
+                                                     FeatureCheapPredicableCPSR]>;
 
 def : ProcNoItin<"cortex-a72",                          [ARMv8a, ProcA72,
                                                          FeatureHWDivThumb,

diff --git a/llvm/lib/Target/ARM/ARMBaseInstrInfo.cpp b/llvm/lib/Target/ARM/ARMBaseInstrInfo.cpp
@@ -558,13 +558,68 @@ bool ARMBaseInstrInfo::DefinesPredicate(
   return Found;
 }
 
-static bool isCPSRDefined(const MachineInstr *MI) {
-  for (const auto &MO : MI->operands())
+bool ARMBaseInstrInfo::isCPSRDefined(const MachineInstr &MI) {
+  for (const auto &MO : MI.operands())
     if (MO.isReg() && MO.getReg() == ARM::CPSR && MO.isDef() && !MO.isDead())
       return true;
   return false;
 }
 
+bool ARMBaseInstrInfo::isAddrMode3OpImm(const MachineInstr &MI,
+                                        unsigned Op) const {
+  const MachineOperand &Offset = MI.getOperand(Op + 1);
+  return Offset.getReg() != 0;
+}
+
+// Load with negative register offset requires additional 1cyc and +I unit
+// for Cortex A57
+bool ARMBaseInstrInfo::isAddrMode3OpMinusReg(const MachineInstr &MI,
+                                             unsigned Op) const {
+  const MachineOperand &Offset = MI.getOperand(Op + 1);
+  const MachineOperand &Opc = MI.getOperand(Op + 2);
+  assert(Opc.isImm());
+  assert(Offset.isReg());
+  int64_t OpcImm = Opc.getImm();
+
+  bool isSub = ARM_AM::getAM3Op(OpcImm) == ARM_AM::sub;
+  return (isSub && Offset.getReg() != 0);
+}
+
+bool ARMBaseInstrInfo::isLdstScaledReg(const MachineInstr &MI,
+                                       unsigned Op) const {
+  const MachineOperand &Opc = MI.getOperand(Op + 2);
+  unsigned OffImm = Opc.getImm();
+  return ARM_AM::getAM2ShiftOpc(OffImm) != ARM_AM::no_shift;
+}
+
+// Load, scaled register offset, not plus LSL2
+bool ARMBaseInstrInfo::isLdstScaledRegNotPlusLsl2(const MachineInstr &MI,
+                                                  unsigned Op) const {
+  const MachineOperand &Opc = MI.getOperand(Op + 2);
+  unsigned OffImm = Opc.getImm();
+
+  bool isAdd = ARM_AM::getAM2Op(OffImm) == ARM_AM::add;
+  unsigned Amt = ARM_AM::getAM2Offset(OffImm);
+  ARM_AM::ShiftOpc ShiftOpc = ARM_AM::getAM2ShiftOpc(OffImm);
+  if (ShiftOpc == ARM_AM::no_shift) return false; // not scaled
+  bool SimpleScaled = (isAdd && ShiftOpc == ARM_AM::lsl && Amt == 2);
+  return !SimpleScaled;
+}
+
+// Minus reg for ldstso addr mode
+bool ARMBaseInstrInfo::isLdstSoMinusReg(const MachineInstr &MI,
+                                        unsigned Op) const {
+  unsigned OffImm = MI.getOperand(Op + 2).getImm();
+  return ARM_AM::getAM2Op(OffImm) == ARM_AM::sub;
+}
+
+// Load, scaled register offset
+bool ARMBaseInstrInfo::isAm2ScaledReg(const MachineInstr &MI,
+                                      unsigned Op) const {
+  unsigned OffImm = MI.getOperand(Op + 2).getImm();
+  return ARM_AM::getAM2ShiftOpc(OffImm) != ARM_AM::no_shift;
+}
+
 static bool isEligibleForITBlock(const MachineInstr *MI) {
   switch (MI->getOpcode()) {
   default: return true;
@@ -590,7 +645,7 @@ static bool isEligibleForITBlock(const MachineInstr *MI) {
   case ARM::tSUBi3: // SUB (immediate) T1
   case ARM::tSUBi8: // SUB (immediate) T2
   case ARM::tSUBrr: // SUB (register) T1
-    return !isCPSRDefined(MI);
+    return !ARMBaseInstrInfo::isCPSRDefined(*MI);
   }
 }
 
@@ -3349,6 +3404,22 @@ ARMBaseInstrInfo::getVLDMDefCycle(const InstrItineraryData *ItinData,
   return DefCycle;
 }
 
+bool ARMBaseInstrInfo::isLDMBaseRegInList(const MachineInstr &MI) const {
+  unsigned BaseReg = MI.getOperand(0).getReg();
+  for (unsigned i = 1, sz = MI.getNumOperands(); i < sz; ++i) {
+    const auto &Op = MI.getOperand(i);
+    if (Op.isReg() && Op.getReg() == BaseReg)
+      return true;
+  }
+  return false;
+}
+unsigned
+ARMBaseInstrInfo::getLDMVariableDefsSize(const MachineInstr &MI) const {
+  // ins GPR:$Rn, pred:$p (2xOp), reglist:$regs, variable_ops
+  // (outs GPR:$wb), (ins GPR:$Rn, pred:$p (2xOp), reglist:$regs, variable_ops)
+  return MI.getNumOperands() + 1 - MI.getDesc().getNumOperands();
+}
+
 int
 ARMBaseInstrInfo::getLDMDefCycle(const InstrItineraryData *ItinData,
                                  const MCInstrDesc &DefMCID,
@@ -4119,7 +4190,8 @@ unsigned ARMBaseInstrInfo::getPredicationCost(const MachineInstr &MI) const {
 
   const MCInstrDesc &MCID = MI.getDesc();
 
-  if (MCID.isCall() || MCID.hasImplicitDefOfPhysReg(ARM::CPSR)) {
+  if (MCID.isCall() || (MCID.hasImplicitDefOfPhysReg(ARM::CPSR) &&
+                        !Subtarget.cheapPredicableCPSRDef())) {
     // When predicated, CPSR is an additional source operand for CPSR updating
     // instructions, this apparently increases their latencies.
     return 1;
@@ -4148,7 +4220,8 @@ unsigned ARMBaseInstrInfo::getInstrLatency(const InstrItineraryData *ItinData,
   }
 
   const MCInstrDesc &MCID = MI.getDesc();
-  if (PredCost && (MCID.isCall() || MCID.hasImplicitDefOfPhysReg(ARM::CPSR))) {
+  if (PredCost && (MCID.isCall() || (MCID.hasImplicitDefOfPhysReg(ARM::CPSR) &&
+                                     !Subtarget.cheapPredicableCPSRDef()))) {
     // When predicated, CPSR is an additional source operand for CPSR updating
     // instructions, this apparently increases their latencies.
     *PredCost = 1;

diff --git a/llvm/lib/Target/ARM/ARMBaseInstrInfo.h b/llvm/lib/Target/ARM/ARMBaseInstrInfo.h
@@ -159,6 +159,24 @@ class ARMBaseInstrInfo : public ARMGenInstrInfo {
 
   bool isPredicable(const MachineInstr &MI) const override;
 
+  // CPSR defined in instruction
+  static bool isCPSRDefined(const MachineInstr &MI);
+  bool isAddrMode3OpImm(const MachineInstr &MI, unsigned Op) const;
+  bool isAddrMode3OpMinusReg(const MachineInstr &MI, unsigned Op) const;
+
+  // Load, scaled register offset
+  bool isLdstScaledReg(const MachineInstr &MI, unsigned Op) const;
+  // Load, scaled register offset, not plus LSL2
+  bool isLdstScaledRegNotPlusLsl2(const MachineInstr &MI, unsigned Op) const;
+  // Minus reg for ldstso addr mode
+  bool isLdstSoMinusReg(const MachineInstr &MI, unsigned Op) const;
+  // Scaled register offset in address mode 2
+  bool isAm2ScaledReg(const MachineInstr &MI, unsigned Op) const;
+  // Load multiple, base reg in list
+  bool isLDMBaseRegInList(const MachineInstr &MI) const;
+  // get LDM variable defs size
+  unsigned getLDMVariableDefsSize(const MachineInstr &MI) const;
+
   /// GetInstSize - Returns the size of the specified MachineInstr.
   ///
   unsigned getInstSizeInBytes(const MachineInstr &MI) const override;

diff --git a/llvm/lib/Target/ARM/ARMSchedule.td b/llvm/lib/Target/ARM/ARMSchedule.td
@@ -147,6 +147,9 @@ def : PredicateProlog<[{
   const ARMBaseInstrInfo *TII =
     static_cast<const ARMBaseInstrInfo*>(SchedModel->getInstrInfo());
   (void)TII;
+  const ARMSubtarget *STI =
+    static_cast<const ARMSubtarget*>(SchedModel->getSubtargetInfo());
+  (void)STI;
 }]>;
 
 def IsPredicatedPred : SchedPredicate<[{TII->isPredicated(*MI)}]>;
@@ -420,3 +423,4 @@ include "ARMScheduleA8.td"
 include "ARMScheduleA9.td"
 include "ARMScheduleSwift.td"
 include "ARMScheduleR52.td"
+include "ARMScheduleA57.td"